Triple
T1991332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rossiya Airlines |
E43256
|
entity |
| Predicate | servesCity |
P82
|
FINISHED |
| Object | Sochi |
E33306
|
NE FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sochi | Statement: [Rossiya Airlines, servesCity, Sochi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sochi Context triple: [Rossiya Airlines, servesCity, Sochi]
-
A.
Sochi
chosen
Sochi is a Russian resort city on the Black Sea coast, known for its subtropical climate, beaches, and as the host of the 2014 Winter Olympics.
-
B.
Kislovodsk
Kislovodsk is a Russian spa and resort city in the North Caucasus, renowned for its mineral springs and mountainous surroundings.
-
C.
Sofya
Sofya is the Russian given name of Sophia Tolstaya, the wife and muse of novelist Leo Tolstoy.
-
D.
Moscow
Moscow is the capital and largest city of Russia, serving as its political, economic, and cultural center.
-
E.
Moscow
Moscow is a fictional character from the Spanish television series "Money Heist" (La Casa de Papel), known as a kind-hearted, blue-collar miner and the father of Denver who participates in the Royal Mint heist.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69a88714cf2c819081644be450b8356e |
completed | March 4, 2026, 7:25 p.m. |
| NER | Named-entity recognition | batch_69abb8451fe8819093531052f4533c36 |
completed | March 7, 2026, 5:31 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae1fdd7b5c8190bf23a138c28857f8 |
completed | March 9, 2026, 1:18 a.m. |
Created at: March 4, 2026, 7:37 p.m.